When using the AI Positron Assistant add-on with Oxygen versions 26.1 or newer, the AI Positron Fix action now leverages the Retrieval-Augmented Generation (RAG) process to enhance the AI's response by using information from the current document, leading to more relevant responses. For more information, see Oxygen AI Positron Assistant - Validation Quick Fixes.

Within the definition of custom actions, you can reference existing functions that are called by the AI engine to interact with the application. This gives actions more context information and allows for more accurate answers to be constructed by the AI. The current available reference values for pre-defined function calls are:

• add_to_toc - Modifies a DITA map and adds a specified topic reference to it.
• find_similar_reusable_content - Retrieves a list of reusable DITA XML components that match keywords provided by the AI.
• get_content_for_document_url - Retrieves the content of a certain document.
• get_corresponding_dita_keyrefs - Can be used to find if there are key definitions for corresponding values.
• get_current_document_marked_up_content - Obtains all text with markup from the current document open in the editor.
• get_current_document_plain_text_content - Obtains all text without markup from the current document open in the editor.
• get_current_editor-file_location - Retrieves the location (absolute path/URL) of the current file that is open in the editor.
• get_related_content_from_project - Retrieves content from the user's local project based on given key words. It is limited to return a maximum of 50k characters and works with Oxygen version 26.1 (latest build) or newer.
• get_related_content_from_webhelp - Returns content from the associated Oxygen Feedback WebHelp system for which a token has been configured in the preferences page.
• get_related_resources_overview_from_project- Retrieves an overview of a maximum of 5 documents that each contain a URL along with the most relevant information (usually titles, key words, short descriptions).
• get_text_around_caret - Obtains size-limited content around the current cursor location within the document open in the editor.
• get_topic_context_in_toc - Returns the hierarchical structure path that references the selected topic from the DITA map that is open in the DITA Maps Manager view, providing context such as its parent, siblings, and surrounding nodes within the DITA map. This is useful for understanding the topic's location in relation to other elements in the DITA map.
• resolve_dita_key_or_content_reference - Resolves a DITA XML key reference, a content key reference, or a content reference to the target text.
• save_document(URL,content) - Saves the document at the specified path and writes content to it. If a resource already exists at the specified URL, the content of the document will be overridden with the new content.

For more information about the function calls, see Oxygen AI Positron Assistant - Function Calls.

You now have the ability to filter the list of actions to exclude those that you do not use. An option was added in the Oxygen AI Positron Assistant preferences page where you can specify which actions will no longer be presented in the list of available actions.

New action types are now available when implementing custom user-specific actions:

• prompt-user - Prompts the user for extra details passed to the action prompt.
• replace-selection-based-on-image-analysis - Uses details obtained from the referenced DITA XML images when performing the action prompt.

The Chat about Code AI action (located in the Development category) is now available and enables users to start a conversation with the AI regarding the code found in the current selection, at the cursor location, or in the whole document. Utilizing this feature, users can easily optimize and rewrite code blocks with the help of the AI Positron Assistant, thus enhancing their overall coding experience and efficiency. This action is available for XSLT, Schematron, XSD, CSS, XQuery, JSON, and JSON Schema documents.

The newly introduced Document Code AI action (located in the Development category) can be used to generate the documentation for selected content, the current node, or the entire document. The generated documentation can then be inserted as an XML comment before the documented code. This feature is applicable to XSLT, XSD, and Schematron documents.

The Generate Code AI action (located in the Development category) allows users to generate code for various editor types (such as XSLT, Schematron, XSD, CSS, XQuery, JSON, and JSON Schema) based on the instruction specified in a selected text from the editor or in a comment preceding the cursor location. It also reuses components found in the current document, making the responses more relevant.

The new Suggest Refactoring AI action (in the Development category) generates a suggestion for refactoring the selected code to simplify it and make it easier to read and understand. This action is available for XSLT and XSD documents.

When utilizing AI actions in Text mode, it is easier to identify the element affected by an AI action. The current element, serving as the context for the action, is highlighted for improved visibility and ease of identification.

GPT-4o was added to the list of models to choose from in the Oxygen AI Positron Assistant preferences page and it is also used as the default model if no other is specified. It is OpenAI's most advanced multi-modal (able to accept text or image inputs) model and it is faster and less expensive than the GPT-4 Turbo model.

When utilizing the Oxygen AI Positron Assistant Enterprise add-on, access to the GPT-4o model is possible when connected to the OpenAI platform.

The GPT-4o-mini AI model was added to the list of available models. According to the OpenAI documentation, it is the most advanced one in the "small models category" and also the least expensive model. You can choose to use this new model on a case-by-case basis or you can configure the connection settings to make it the default model used for all actions.

The GPT-4 Turbo Preview model, which could be used by the AI Positron Assistant with the cloud-based Oxygen AI Positron Service or by the Enterprise add-on when connecting to OpenAI, was replaced with the final GPT-4 Turbo engine release.

The credit system has been updated to enhance cost efficiency. Now, input tokens and output tokens are treated differently when calculating consumed credits, with input tokens being less expensive than output tokens.

An Oxygen XML Enterprise edition license for Oxygen XML Editor, Author, and Developer products now includes access to the Oxygen AI Positron Assistant Enterprise add-on at no extra cost. The subscription license for Oxygen AI Positron Assistant Enterprise add-on remains available for Oxygen Professional, Academic, and Personal edition users that want to use the AI Positron Assistant Enterprise Add-on.

The Enterprise version of the Oxygen AI Positron Assistant add-on introduces a new connector for Anthropic Claude, along with the existing connectors for OpenAI and Microsoft Azure OpenAI Service, thus allowing users to connect directly to Anthropic Claude as well.

For the Enterprise version of Oxygen AI Positron Assistant, the Microsoft Azure OpenAI Service connector now supports authentication using Microsoft Entra ID, offering improved security and flexibility. Environment variables can be used for various authentication methods, including service principal and username/password authentication.

When directly initiating a new chat with the AI (without invoking an action), the detected document type and any content selected in the main editor area is automatically passed as context for the conversation. This feature allows you to get responses more tailored for that specific document.

The signatures of the AI XPath functions ai:transform-content and ai:verify-content were modified to allow adding a conversation history when the functions are used. You can add multiple pairs of user-agent data that will be passed to the AI as the history of the conversation. This can be used for more complex actions that need to also set a context for the AI operation.

The content received from the AI engine is presented in the chat response area either with XML syntax highlight or Markdown syntax highlight depending on the response content.

URL links present in the chat response area can be opened by pressing Ctrl/Command and then mouse clicking on the link.

Information regarding favorite prompts, chat history, or AI XPath functions are stored encrypted in the options file. The Retrieval-Augmented Generation (RAG) preferences page has new security-related options to enable reading and writing content in the project or to control if the end user is prompted to allow the use of function calls for particular actions.

The Toggle Comment action encloses the currently selected content in a comment that is ignored by the parser or removes an existing comment. This action is now available for all document types that support comments. For example, toggling comments is now possible in RNC, SQL, Batch, Java, JavaScript, C, C++, PHP, and PowerShell documents.

The XQuery Builder view that allows you to compose complex XQuery expressions and execute them over the currently edited document now supports running the XQuery over JSON documents.

Our latest JSON editing features streamline your workflow by ensuring content is consistently formatted. You can now specifically indent selected sections within JSON documents using the Indent Selection action found in the contextual menu, enhancing code readability without altering the entire document. Additionally, any content added through the content completion assistant or pasted into the editor is automatically indented, removing the need for manual formatting and saving you valuable time.

The transparency level for the property names that are displayed after the ending brackets in JSON documents can now be customized. There is a new option in the Options->Preferences->Editor->Edit Modes->Text page where the transparency level can be adjusted according to your needs.

When you move your cursor over a property while editing a JSON document, a tooltip appears with detailed documentation about that particular property, based upon information from the associated JSON schema.

When adding content using code templates in JSON or JSON Schema documents, a final comma is now inserted if it is required by the particular context.

The JSON Schema Validator add-on has been enhanced with the integration of local meta-schema usage, advanced recursion prevention techniques, and a series of bug fixes.

When you move your cursor over a property while editing a YAML document, a tooltip appears with detailed documentation about that particular property, based upon information from the associated JSON schema.

The schemas that are used for validation and content completion in HTML and XHTML documents was updated to support the latest content model for the <hgroup> element. For example, <h1> through <h6> and <p> child elements are now allowed within <hgroup> elements in the updated schemas.

Saxon added more extension functions and instructions in the Saxon namespace, as well as experimental implementations for version 4.0 extensions. These functions are now supported and included in the list of proposals of the content completion assistant. Some examples include: fn:duplicate-values(), fn:void(), fn:every(), map:of-pairs(), array:of-members(), array:split(), map:pair(), and many more. For details, see https://www.saxonica.com/documentation12/index.html#!changes/extensions.

The saxon:evaluate(), saxon:eval(), and saxon:expression() extension functions that were previously dropped in the last version were reinstated for the benefit of XQuery users when the exl:evaluate instruction is not available.

Support was added for XQuery 4.0. This means that you can run XQuery 4.0 transformation scenarios from the editor or from the XQuery builder view and you can edit XQuery 4.0 documents with complete support for content completion, syntax highlights, and more.

The xsl:initial-template support has been activated for XSLT 4.0. This type of template previously was supported in XSLT 3.0, and it is now also available for XSLT 4.0 documents.

The sqf:default-fix attribute from the Schematron Quick Fix specification is now collected and used by the Apply all default quick fix proposals action. The action will automatically apply all default quick fixes defined the Schematron file.

Latex equations that are embedded in Markdown content are preserved as <foreign> elements in the DITA preview pane and when publishing Markdown content referenced in a DITA map. Furthermore, with the help of additional plugins, the Latex content can be rendered as an equation in the DITA preview pane and the published content.

Some of the syntax highlight colors for Markdown were changed for better readability. Markdown code blocks that contain XML, XSLT, XML Schema, or DTD content now display specific syntax highlights for the particular language, making the code more distinguishable and recognizable.

Various improvements were made to the Git Client add-on:

• A new button was added above the commit message area to create an AI-generated commit message using the Oxygen AI Positron Assistant.
• It is now possible to sign commits using GPG keys.
• If there are unpulled changes detected when creating a new branch, a confirmation dialog box is displayed where you can choose whether or not to pull the changes before processing the branch creation.
• If you attempt to merge a branch into the current one and unpulled changes are detected on the branch being merged, a warning message will appear. This allows you to bring that branch up-to-date first (by performing a pull) and then the merge is automatically retried.
• Local branches that are linked to remote branches that no longer exist are now detected and reported.
• You can now pull changes from a remote branch other than the one being tracked.
• When performing tasks such as switching or merging branches, restarting a merge, and many others, the progress of the operation is now shown when it takes more than two seconds to complete.
• When comparing two revisions or opening the compare editor to resolve merge or rebase conflicts, the comparison tool now provides more detailed information about the commits involved.
• The JGit component was updated to version 7.0.0.
• Updated the minimum required version of Oxygen to 26.1.
• Fixed various bugs.

The Oxygen Feedback Connector add-on can now be used with topics opened from Content Management Systems (CMS) or other remote storage systems.

The Terminology Checker add-on received the following updates:

• Various security/component updates were implemented.
• The end user is now allowed to avoid showing the choice to remove matched terms that did not have any proposed suggestions.

A previous limitation was solved for the Compare Directories command-line script making it now possible to use the -enx XPathExprToExcludeNodes argument. It allows you to specify an XPath expression that will exclude certain nodes from the comparison. This option can now be used without any limitation, regardless of the format chosen for the comparison report.

More flexibility was added in the Compare Directories command-line script in regard to the handling of certain cases as requested by users with the addition of two new options. The -a dirPathAlias argument can be used to specify an alias for the directory path that will be displayed in the HTML-formatted operation report instead of a long directory path. The -sl suppressLinks argument can be set to true to suppress links to the compared directories and files that are displayed in the HTML operation report.

Various batch operations (Spell check in Files, Find in files, Validate and check for completeness, Search References, Project Selected Resources Validation) are now performed in the background with the progress displayed in the status bar instead of blocking the entire application with a modal progress dialog box while the operation is processing.

The performance of validation operations on large file sets was significantly improved. These improvements are most noticeable when invoking a validation operation either from the Project view or from the command line via a validation script.

The performance speed was improved when editing attributes in DocBook XML documents that contain lots of links.

Editing and validation support is now provided for AsyncAPI documents version 3.0. This includes support for content completion, automatic validation, and editing AsyncAPI 3.0 documents in Text or Author mode. New document templates are also available for AsyncAPI 3.x documents.

For DITA XML documents, the order of results displayed in the Open/Find Resources dialog box is determined by the element context in which the searched words are found. For example, if documents contain the particular searched words within <title>, <keyword>, <shortdesc>, or <uicontrol> elements, their ranking will be higher than for documents where the particular searched words are only found within plain paragraph text.

If a loaded plugin delays the startup of the application for more than 15 seconds, the plugin will continue to be loaded on a thread and the startup will continue. This helps to reduce possible hangups since the application will continue loading without waiting for the plugin to fully initialize.

The version of OpenJDK that is bundled with the installation kits for providing the Java Runtime Environment was updated to version 17.0.13 from Eclipse Adoptium.

Oxygen 27.0 has been fully tested on macOS 15 (Sequoia) and it is now officially supported.

Updated the bundled spell checker dictionary used for US English to contain more recently added words.

The Eclipse plugin was updated to fully support Eclipse 4.33.

Updated the Apache Batik library to version 1.18.

Updated the Apache FOP library to version 2.10.

Updated the Apache Lucene Indexer libraries to version 9.11.1.

Updated the Apache HTTP Client libraries to version 4.5.14.

Updated the Apache Sanctuario libraries to version 4.0.2.

Updated the DOMPurify library to version 2.5.6.

Updated the bundled TEI schemas to version 4.8.1.

Updated the bundled TEI XSLT stylesheets to version 7.57.1.

Updated the XSpec framework to version 3.1.2.

Support for the insecure File Transfer Protocol (FTP) was removed.

Support for authentication using the Kerberos protocol was deprecated and will be removed in a future version.

The DocBook to WebHelp Classic transformation scenario is no longer supported and has been removed from the application.

Syncro Soft, the company that develops the Oxygen XML suite of products, has earned the ISO/IEC 27001:2022 certification, demonstrating a strong commitment to implementing top-tier information security practices and ensuring that the users' data is protected to the highest standards.

The privacy section of the application installer allows disabling the support to install all add-ons or Oxygen AI-specific add-ons. These settings can also be set when the installer is running in unattended mode.

Two new methods were added to the OxygenUIComponentsFactory API. The createRadioMenuItem(Action) method can be used to create a radio button component, while the createCheckBoxMenuItem(Action) method can be used to create a checkbox menu item.

A new StandalonePluginWorkspace.createAuthorPreviewComponentProvider() API was added to create a simple read-only preview component based on the Author visual editor that can be used to render XML documents visually (for example, in a side view).

A new ProjectIndexer.search(String, int) API method was added that allows searching for keywords in the current indexed project to retrieve documents that contain the keywords.

A new WSXMLTextEditorPage.getXPath(int, boolean) API method was added that can be used to obtain the XPath expression for an element at a certain location in the XML text editor.

A new ro.sync.exml.workspace.api.componentscollector.IComponentsProvider.getAllComponents(URL) method was added for obtaining the global components from the current editor. It can be obtained from the PluginWorkspace.getComponentProvider() API.

A new ro.sync.exml.workspace.api.componentscollector.IXSLComponentInfo API adds two methods (getMatch and getMode) for providing more accurate information about XSLT components.

A new XMLUtilAccess.getXMLStructureAsDTD API method was added to get the structure of the specified XML document as a DTD.

A new ValidationUtilAccess.validateResources API method was added to provide a reader for validation problems.